Best subagents skills, page 19

This skill should be used when an agent is deciding whether to author a dynamic workflow — a self-authored, ephemeral multi-agent harness — for a task.

Habitat-Thinking/ai-literacy-superpowers

Fan out work to multiple parallel agents and collect results in a MoonBit Golem project.

golemcloud/golem

Fan out work to multiple parallel agents and collect results in a Rust Golem project.

golemcloud/golem

Fan out work to multiple parallel agents and collect results in a Scala Golem project.

golemcloud/golem

Fan out work to multiple parallel agents and collect results in a TypeScript Golem project.

golemcloud/golem

Run data analytics and produce publication-quality tables and visualizations for social science research.

joshzyj/open-scholar-skill

Launch Codex CLI as an isolated subagent for bounded coding, review, or verification tasks.

majiayu000/claude-skill-registry

Review changed code for reuse, quality, and efficiency using three parallel disposable subagents.

NikiforovAll/claude-code-rules

A skill your agent uses when executing implementation plans with independent tasks in the current session - dispatches fresh subagent for each task with code review between tasks, enabling fast…

aiskillstore/marketplace

Run the code and documentation simplification passes together over one scope, launching every review sub-agent concurrently before applying a single round of fixes.

tobihagemann/turbo

Reduces token usage from paid providers by offloading work to local LM Studio models.

sundial-org/awesome-openclaw-skills

通过基于规模的规划、审批、实现、验证和上报流程协调子智能体。用于将工作路由给子智能体、执行已批准的工作计划，或恢复自主执行时使用。

shinpr/ai-coding-project-boilerplate

Non-interactive deep research pipeline for specialist subagents.

magnus919/hermes-profiles

Controls the cmux macOS terminal app (Ghostty-based, AI-agent-aware) via its CLI socket API.

glebis/claude-skills

Use during the validate stage to produce the LLM-review half of validate.json.

sunblaze-ucb/vero

Deep single-RL-job health probe → a KILL / NO-KILL / ERROR recommendation for the supervisor.

open-thoughts/OpenThoughts-Agent

Polish your own diff by hand with KISS/DRY and local style — the pre-handoff pass, not a test run and not a subagent sweep.

OutThisLife/brooklyn-skills

Turn an OpenClaw agent into an autonomous AI Chief that runs a business.

LeoYeAI/openclaw-master-skills

Multi-agent parallel orchestration for OpenClaw. An agent skill from LeoYeAI/openclaw-master-skills.

LeoYeAI/openclaw-master-skills

Orchestrates business idea validation via parallel sub-agents: Lean Canvas, JTBD, market/competitive/feasibility research, SWOT/PESTLE, and a weighted scorecard with verdict.

Mathews-Tom/armory

Coordinate complex engineering work across bounded subagents while protecting the main context, preventing edit conflicts, and measuring whether delegation was worthwhile.

hashgraph-online/awesome-codex-plugins

Provider-neutral deep-research orchestration for brainstorming, technology choices, comparisons, and state-of-the-art surveys.

tamdogood/builder-essential-skills

Design and build custom Claude Code agents with effective descriptions, tool access patterns, and self-documenting prompts.

majiayu000/claude-skill-registry

Distill a book into a coherent set of executable skills. An agent skill from majiayu000/claude-skill-registry.

majiayu000/claude-skill-registry

Create custom subagents for specialized AI tasks. An agent skill from majiayu000/claude-skill-registry.

majiayu000/claude-skill-registry

Comprehensive Claude Code telemetry via 10 hooks capturing sessions, conversations, tools, subagents, context, permissions, and repository analytics.

majiayu000/claude-skill-registry

Query and analyze Claude Code observability data (metrics, logs, traces).

majiayu000/claude-skill-registry

Autonomous TDD development loop with parallel agent swarm, category evolution, and convergence detection.

majiayu000/claude-skill-registry

Compute metrics for Claude Code sessions. An agent skill from majiayu000/claude-skill-registry.

majiayu000/claude-skill-registry

Searches multiple web sources, synthesizes findings, and produces cited research reports using delegated subagents.

majiayu000/claude-skill-registry

Operational framework for the DAAF orchestrator. An agent skill from brycewang-stanford/Auto-Empirical-Research-Skills.

brycewang-stanford/Auto-Empirical-Research-Skills

Create a workflow command that orchestrates multi-step execution through sub-agents with file-based task prompts

NeoLabHQ/context-engineering-kit

Launch a meta-judge then a judge sub-agent to evaluate results produced in the current conversation

NeoLabHQ/context-engineering-kit

Launch an intelligent sub-agent with automatic model selection based on task complexity, specialized agent matching, Zero-shot CoT reasoning, and mandatory self-critique verification

NeoLabHQ/context-engineering-kit

Parallel Agent Type Contracts

parcadei/Continuous-Claude-v3

Parallel Agent Orchestration

parcadei/Continuous-Claude-v3

Autonomous PR merge pipeline. An agent skill from davepoon/buildwithclaude.

davepoon/buildwithclaude

Use at the start of any conversation about a startup idea, product validation, founder strategy, or work inside a startup/ workspace.

davepoon/buildwithclaude

Recovery strategy when a subagent is stuck on a hard task. An agent skill from opensage-agent/opensage-adk.

opensage-agent/opensage-adk

Practices to apply when taking a code-review assignment. An agent skill from awebai/aweb.

awebai/aweb

Guide for writing fullsend augmentation skills and sub-agents that work alongside shipped defaults.

fullsend-ai/fullsend

A skill your agent uses when Codex or OpenCode repeats avoidable mistakes, keeps guessing after failures, fails to trigger an expected skill/workflow/subagent, or the user corrects agent behavior…

skuramatata/my-pi-agent

Этот скилл MUST быть вызван когда tasks.md готов и требуется автономное параллельное выполнение субагентами (implementer + reviewer на каждую задачу).

Arman-Kudaibergenov/1c-ai-development-kit

Этот скилл MUST быть вызван когда есть design.md и нужно разбить доработку на атомарные задачи (2-5 мин) с точными путями файлов и критериями проверки в tasks.md.

Arman-Kudaibergenov/1c-ai-development-kit

Apply when implementing features, fixing bugs, debugging errors, investigating failures, tracing root causes, reviewing tech debt, tracing issues, planning fixes, or completing any task.

ZaxbyHub/opencode-swarm

Run and resume the CatGo md-orchestration poll loop — delegate each poll to a subagent (keep main context lean), verify convergence by force, auto-advance each converged species per-species…

Hello-QM/catgo-LRG

Orchestrates the full code-to-Figma rebuild workflow for a web application.

bitovi/ai-enablement-prompts

Design, create, audit, and improve Claude Agent Skills with expert-level progressive disclosure.

curiositech/some_claude_skills